Hyperspectral Image Denoising By Combining Ground Object Features with Low-Rank Characteristics

Dongmei Huang; Yonglan Li; Minghua Zhang; Wei Song

doi:10.3788/LOP57.121102

Laser & Optoelectronics Progress, Volume. 57, Issue 12, 121102(2020)

Hyperspectral Image Denoising By Combining Ground Object Features with Low-Rank Characteristics

Dongmei Huang^1,2, Yonglan Li¹, Minghua Zhang^1、*, and Wei Song¹

Author Affiliations

¹College of Information Technology, Shanghai Ocean University, Shanghai 201306, China

²Shanghai University of Electric Power, Shanghai 200090, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(11)

Fig. 1. HSI low rank feature. (a) Local block; (b) object block

Download full size

Fig. 2. GTLR noise reduction process. (a) Using spatial-spectral low rank of object block; (b) using global image spectral low rank

Download full size

Fig. 3. Comparison of PSNR values of noise reduction results

Download full size

Fig. 4. Comparison of SSIM values of noise reduction results

Download full size

Fig. 5. Comparison of FSIM values of noise reduction results

Download full size

Fig. 6. Band 1 noise reduction results of Indian Pines image. (a) Original image; (b) LRMR; (c) NAILRMA; (d) proposed method

Download full size

Fig. 7. Band 2 noise reduction results of Indian Pines image. (a) Original image; (b) LRMR; (c) NAILRMA; (d) proposed method

Download full size

Fig. 8. Band 103 noise reduction results of Indian Pines image. (a) Original image; (b) LRMR; (c) NAILRMA; (d) proposed method

Download full size

Table 1. Noise reduction results for simulated noise case 1
View table
Table 1. Noise reduction results for simulated noise case 1
Index LRMR NAILRMA R-GTLR C-GTLR
SNR /dB 22.8325 22.0547 21.3575 21.5710
MPSNR /dB 31.2309 33.5371 33.8541 33.9788
MSSIM 0.8428 0.8806 0.9205 0.9215
MFSIM 0.9144 0.9337 0.9215 0.9487

Table 2. Noise reduction results for simulated noise case 2
View table
Table 2. Noise reduction results for simulated noise case 2
Index LRMR NAILRMA R-GTLR C-GTLR
SNR /dB 24.2425 27.5657 32.2450 32.6148
MPSNR /dB 41.2179 39.5988 43.9174 44.2105
MSSIM 0.9536 0.9643 0.9956 0.9958
MFSIM 0.9702 0.9772 0.9949 0.9951

Table 3. Noise reduction results for simulated noise case 3
View table
Table 3. Noise reduction results for simulated noise case 3
Index LRMR NAILRMA R-GTLR C-GTLR
SNR /dB 21.8048 21.0537 27.3946 27.7530
MPSNR /dB 39.2026 38.6956 43.0522 43.3406
MSSIM 0.9352 0.9581 0.9888 0.9889
MFSIM 0.9627 0.9728 0.9926 0.9929

Tools

Get Citation

Copy Citation Text

Dongmei Huang, Yonglan Li, Minghua Zhang, Wei Song. Hyperspectral Image Denoising By Combining Ground Object Features with Low-Rank Characteristics[J]. Laser & Optoelectronics Progress, 2020, 57(12): 121102

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites